INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Izan

-0.77

pmwiki

-0.72

 Photographer

-0.68

 ILCS

-0.68

pid

-0.68

atican

-0.63

Use

-0.62

PB

-0.61

Eat

-0.61

culosis

-0.61

POSITIVE LOGITS

hers

0.88

hel

0.85

hem

0.75

heon

0.73

chel

0.72

hed

0.71

ieu

0.69

hes

0.69

rase

0.68

ourgeois

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.